© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8129
    Prev
    Next
    INDEX
    Explanations

    serif, Sharif, sheriff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ു
    3.08
    वर
    2.98
    r
    2.92
    加坡
    2.74
    aps
    2.71
    те
    2.71
    ிறது
    2.67
     Remarkably
    2.59
    ตรฐาน
    2.48
    కు
    2.45
    POSITIVE LOGITS
    werden
    2.79
    cribing
    2.54
     behold
    2.45
    successor
    2.43
     Umm
    2.43
    bmod
    2.41
    ideon
    2.40
    诌
    2.39
    есть
    2.36
     tät
    2.36
    Activations Density 0.018%

    No Known Activations